2021/08/02 by Marco Steinbrink, Steinbrink, Marco, Philipp Koch +5
Computer Science · Engineering · #FOS: Computer and information sciences #Opportunistic and Delay-Tolerant Networks #Robotic Path Planning Algorithms #Robotics (cs.RO) #Robotics and Sensor-Based Localization
paper · pdf · doi:10.48550/arxiv.2108.01012
openalex publication_date 2021/08/02 · openalex created_date 2022/07/25 · openalex updated_date 2026/07/28
In this paper, a novel approach is introduced which utilizes a\nRapidly-exploring Random Graph to improve sampling-based autonomous exploration\nof unknown environments with unmanned ground vehicles compared to the current\nstate of the art. Its intended usage is in rescue scenarios in large indoor and\nunderground environments with limited teleoperation ability. Local and global\nsampling are used to improve the exploration efficiency for large environments.\nNodes are selected as the next exploration goal based on a gain-cost ratio\nderived from the assumed 3D map coverage at the particular node and the\ndistance to it. The proposed approach features a continuously-built graph with\na decoupled calculation of node gains using a computationally efficient ray\ntracing method. The Next-Best View is evaluated while the robot is pursuing a\ngoal, which eliminates the need to wait for gain calculation after reaching the\nprevious goal and significantly speeds up the exploration. Furthermore, a grid\nmap is used to determine the traversability between the nodes in the graph\nwhile also providing a global plan for navigating towards selected goals.\nSimulations compare the proposed approach to state-of-the-art exploration\nalgorithms and demonstrate its superior performance.\n